CN110208658B - Method for performing multivariate complementary cross validation on partial discharge diagnosis result - Google Patents
Method for performing multivariate complementary cross validation on partial discharge diagnosis result Download PDFInfo
- Publication number
- CN110208658B CN110208658B CN201910433085.5A CN201910433085A CN110208658B CN 110208658 B CN110208658 B CN 110208658B CN 201910433085 A CN201910433085 A CN 201910433085A CN 110208658 B CN110208658 B CN 110208658B
- Authority
- CN
- China
- Prior art keywords
- detection
- fault
- partial discharge
- diagnosis
- detection technology
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 73
- 208000028659 discharge Diseases 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000000295 complement effect Effects 0.000 title claims abstract description 9
- 238000002790 cross-validation Methods 0.000 title claims abstract description 8
- 238000001514 detection method Methods 0.000 claims abstract description 222
- 238000005516 engineering process Methods 0.000 claims abstract description 127
- 238000013102 re-test Methods 0.000 claims abstract description 7
- 238000004088 simulation Methods 0.000 claims description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 7
- 239000013589 supplement Substances 0.000 claims description 6
- 238000004587 chromatography analysis Methods 0.000 claims description 5
- 239000000126 substance Substances 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 abstract description 10
- 238000009529 body temperature measurement Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 230000003534 oscillatory effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000010259 detection of temperature stimulus Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Relating To Insulation (AREA)
Abstract
The invention relates to a method for performing multivariate complementary cross validation on a partial discharge diagnosis result, which comprises the following steps of: carrying out partial discharge fault detection on the power equipment by using various partial discharge detection technologies; if the detection result of one partial discharge detection technology is judged that the power equipment has partial discharge faults, the partial discharge detection technology is taken as a dominant detection technology, and the detection result is given; the method comprises the following steps of taking other partial discharge detection technologies as an auxiliary detection technology set, and carrying out multiple auxiliary detections on the power equipment from multiple aspects; selecting whether to retest the power equipment or not according to the conditions of the multiple auxiliary detections, and simultaneously adjusting the diagnosis confidence coefficient of the leading detection technology; and comparing the diagnosis data of the leading detection technology with the expert database set to further confirm the diagnosis. The invention solves the problem of unreliable analysis results caused by analyzing one-sidedness of a single detection technology, and avoids some specific faults from being ignored, thereby improving the accuracy of fault diagnosis.
Description
Technical Field
The invention belongs to the technical field of electrical variable measurement, and particularly relates to a method for performing multivariate complementary cross validation on a partial discharge diagnosis result.
Background
At present, the insulation performance of electric power equipment is mainly analyzed and judged by detecting partial discharge of the electric power equipment. Various physical quantities accompanying the partial discharge can be detected by different detection techniques such as detecting temperature by infrared, chemical components by micro water or oil chromatography, electromagnetic wave intensity by UHF, high frequency, or the like, ultrasonic wave intensity by AE, and the like. In practical applications, the above detection technologies are all adopted, and detection data are all saved, but the diagnosis and analysis of the insulation performance of the power equipment still have the defects of inaccuracy, low reliability and the like due to the following problems:
1. the detection technologies are isolated when used and analyzed, and the reason is mainly that the existing detection equipment is designed according to different physical quantities, and various physical quantity comprehensive detection equipment is not provided, so that detection data of different physical quantities are divided into two parts, and interaction with other data is not performed. Therefore, the analysis processing of the current partial discharge conclusion leads to one-sidedness of the analysis result, and the reliability of the given analysis result is not high. For example, for the detection technology in the electromagnetic field, the detected data is easily affected by external electromagnetic interference, so that in many cases, the power equipment is judged to have partial discharge fault through wrong analysis.
2. In field application, because the service experience of field detection personnel is high or low and the directivity is strong, especially under the condition that the current partial discharge workload is greatly increased but the number of the field personnel with experience is not correspondingly increased, the diagnosis and analysis of field data often excessively depend on the algorithm provided by a detection device manufacturer, but the accuracy of the algorithms of different manufacturers is different in different application occasions from the practical application, which is related to the algorithm training method and data of the manufacturer.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method for performing multivariate complementary cross validation on a partial discharge diagnosis result, which has the advantages of reasonable design, high precision, accuracy and reliability.
The technical problem to be solved by the invention is realized by adopting the following technical scheme:
a method for performing multivariate complementary cross validation on partial discharge diagnostic results comprises the following steps:
step 1, carrying out partial discharge fault detection on the power equipment by using various partial discharge detection technologies;
step 2, if the detection result of one of the partial discharge detection technologies is judged to have a partial discharge fault, the partial discharge detection technology is used as a dominant detection technology to give a detection result; meanwhile, the rest other partial discharge detection technologies are used as an auxiliary detection technology set to perform multiple auxiliary detections on the power equipment from multiple aspects;
step 3, selecting whether to retest the power equipment or not according to the conditions of the multiple auxiliary detections, and simultaneously adjusting the diagnosis confidence coefficient of the leading detection technology;
and 4, comparing the diagnosis data of the leading detection technology with the expert database set, and further determining the diagnosis.
The various partial discharge detection techniques in step 1 include a partial discharge detection technique for detecting temperature by infrared, a partial discharge detection technique for detecting chemical components by micro-water or oil chromatography, a partial discharge detection technique for detecting electromagnetic wave intensity by UHF and high frequency, and a partial discharge detection technique for detecting ultrasonic wave intensity by AE.
The detection result of the dominant detection technology in the step 2 comprises detection data, a fault type with the highest diagnosis possibility and the occurrence probability thereof.
The specific implementation method of the step 3 comprises the following steps:
step 3.1, if the auxiliary detection technology is concentrated with two or more detection technologies, judging that the power equipment has faults, improving the diagnosis confidence of the main detection technology, and executing step 4; if the auxiliary detection technology set only has the detection result of one detection technology to judge that the power equipment has faults, executing a step 3.2; if the auxiliary detection technology set does not have a detection result of one detection technology to judge that the power equipment has a fault, executing a step 3.3;
3.2, retesting the power equipment by the auxiliary detection technology set, if the auxiliary detection technology set has two or more detection results of the detection technologies in retesting to judge that the power equipment has faults, improving the diagnosis confidence of the leading detection technology, and executing the step 4; if the detection results of two or more detection technologies do not exist yet, the power equipment is judged to have faults, the diagnosis confidence coefficient of the leading detection technology is reduced, meanwhile, if the occurrence probability corresponding to the fault type given by the leading detection technology is not less than 60%, the step 4 is executed, and if the occurrence probability corresponding to the fault type given by the leading detection technology is less than 60%, the diagnosis conclusion is normal;
3.3, retesting the power equipment by an auxiliary detection technology set; if the auxiliary detection technology set has two or more detection results of the detection technologies in the retest to judge that the power equipment has faults, the diagnosis confidence coefficient of the leading detection technology is improved, and the step 4 is executed; if the detection results of two or more detection technologies do not determine that the power equipment has a fault, the diagnosis confidence of the leading detection technology is reduced, meanwhile, if the occurrence probability corresponding to the fault type given by the leading detection technology exceeds 80%, step 4 is executed, and if the occurrence probability corresponding to the fault type given by the leading detection technology is lower than 80%, the diagnosis conclusion is normal.
The specific implementation method of the step 4 comprises the following steps:
aiming at the condition that the diagnosis confidence coefficient is improved, comparing the detection data given by the leading detection technology with the data of the familial fault library, and further determining whether the data is the familial fault; if the detected data is the known familial fault, the diagnosis conclusion is that the fault is detected, and the detected data is listed in a familial fault library for data supplement after the later diagnosis is confirmed; if unknown familial faults exist, comparing the data of the field fault case library with the data of the laboratory fault simulation library to further determine the fault type, and after the diagnosis is confirmed in the later period, listing the fault type in the familial fault library for data supplement;
aiming at the condition that the diagnosis confidence coefficient is reduced, comparing the detection data given by the leading detection technology with the data of the familial fault library to further determine whether the data is the familial fault, and if the data is the known familial fault, judging that the diagnosis conclusion is the fault; if the unknown familial fault is detected, comparing the data of the field fault case library with the data of the laboratory fault simulation library, if the probability of occurrence of the fault type given again after comparison is not less than 60%, determining that the fault is detected, if the probability of occurrence of the fault type given again after comparison is less than 60%, otherwise, determining that the fault is normal.
The expert library set in the step 4 comprises a familial fault library, a field fault case library and a laboratory fault simulation library.
The invention has the advantages and positive effects that:
the invention carries out complementary verification on the analysis result through different partial discharge diagnosis technologies, and solves the problem of unreliable analysis result caused by the analysis one-sidedness of a single detection technology; and the fault diagnosis result is cross-verified through a large amount of fault case data and laboratory fault simulation data of the expert database, and specific familial faults are screened through the familial fault data of the expert database, so that some specific faults are prevented from being ignored, and the accuracy of fault diagnosis is improved.
Drawings
FIG. 1 is a process flow diagram of the present invention.
Detailed Description
The embodiments of the present invention will be described in detail with reference to the accompanying drawings.
A method for performing multivariate complementary cross validation on partial discharge diagnostic results, as shown in fig. 1, comprising the following steps:
step 1, carrying out partial discharge fault detection on the power equipment by using various partial discharge detection technologies.
In this step, various partial discharge detection techniques include infrared detection of temperature, detection of chemical components by micro-water or oil chromatography, detection of electromagnetic wave intensity by UHF, high frequency, and the like, and detection of ultrasonic wave intensity by AE.
Step 2, if the detection result of one of the partial discharge detection methods judges that the power equipment has partial discharge faults, the partial discharge faults are taken as a leading detection technology, and the detection result is given; meanwhile, the rest other partial discharge detection technologies are used as an auxiliary detection technology set, and the power equipment is subjected to multiple items of auxiliary detection in various aspects.
After detection is finished, the leading detection technology automatically generates multiple possible fault types of the power equipment and the occurrence probability of each fault type according to detection data, and then the fault type with the highest occurrence probability is used as a diagnosis result. The detection result of the dominant detection technology comprises detection data, the fault type with the highest diagnosis possibility and the occurrence probability thereof.
For example: if the electrical equipment is a GIS, the partial discharge detection techniques may include UHF, AE, HFCT, micro-water detection, infrared temperature measurement, and the like. If the detection result of the UHF indicates that the GIS has a fault, the UHF is used as a leading detection technology to give a detection result, other detection technologies (including AE, HFCT, micro-water detection, infrared temperature measurement and the like) are used as an auxiliary detection technology set to carry out multiple auxiliary detections on the GIS from multiple aspects, and the detection result of the UHF is supplemented by the auxiliary detection results.
If the power equipment is a transformer, the partial discharge detection technology can comprise UHF, AE, HFCT, oil chromatography detection results, infrared temperature measurement and the like, if the detection result of the HFCT considers that the transformer has a fault, the HFCT is taken as a leading detection technology to give a detection result, and other detection technologies (comprising AE, UHF, micro-water detection, infrared temperature measurement and the like) are taken as an auxiliary detection technology set to perform multiple auxiliary detections on the transformer from multiple aspects, and the detection result of the HFCT is supplemented by the auxiliary detection results.
If the power equipment is a cable, the partial discharge detection technology can comprise AE, HFCT, grounding circulation, 0.1Hz ultralow frequency, oscillatory wave, infrared temperature measurement and the like, if the detection result of the AE considers that the transformer has a fault, the AE is taken as a leading detection technology to give a detection result, and other detection technologies (comprising HFCT, grounding circulation, 0.1Hz ultralow frequency, oscillatory wave, infrared temperature measurement and the like) are taken as an auxiliary detection technology set to perform multiple auxiliary detections on the cable from multiple aspects, and the detection result of the AE is supplemented by the auxiliary detection results.
And 3, selecting whether to retest the power equipment or not according to the auxiliary detection condition, and adjusting the diagnosis confidence coefficient of the leading detection technology.
The specific implementation method of the step comprises the following steps:
step 3.1, if the auxiliary detection technology is concentrated with two or more detection technologies, judging that the power equipment has faults, improving the diagnosis confidence of the main detection technology, and executing step 4; if the auxiliary detection technology set only has the detection result of one detection technology to judge that the power equipment has faults, executing a step 3.2; if the detection result of none of the detection technologies in the auxiliary detection technology set determines that the power equipment has a fault, step 3.3 is executed.
3.2, retesting the power equipment by the auxiliary detection technology set, if the auxiliary detection technology set has two or more detection results of the detection technologies in retesting to judge that the power equipment has faults, improving the diagnosis confidence of the leading detection technology, and executing the step 4; if the detection results of two or more detection technologies do not determine that the power equipment has a fault, the diagnosis confidence of the leading detection technology is reduced, meanwhile, if the occurrence probability corresponding to the fault type given by the leading detection technology is not less than 60%, step 4 is executed, and if the occurrence probability corresponding to the fault type given by the leading detection technology is less than 60%, the diagnosis conclusion is normal.
3.3, retesting the power equipment by an auxiliary detection technology set; if the auxiliary detection technology set has two or more detection results of the detection technologies in the retest to judge that the power equipment has faults, the diagnosis confidence coefficient of the leading detection technology is improved, and the step 4 is executed; if the detection results of two or more detection technologies do not determine that the power equipment has a fault, the diagnosis confidence of the leading detection technology is reduced, meanwhile, if the occurrence probability corresponding to the fault type given by the leading detection technology exceeds 80%, step 4 is executed, and if the occurrence probability corresponding to the fault type given by the leading detection technology is lower than 80%, the diagnosis conclusion is normal.
And 4, comparing the diagnosis data of the leading detection technology with the expert database set, and further determining the diagnosis.
The expert library set used in the step comprises a familial fault library, a field fault case library and a laboratory fault simulation library. The specific implementation method of the step comprises the following steps:
aiming at the condition that the diagnosis confidence coefficient is improved, comparing the detection data given by the leading detection technology with the data of the familial fault library, and further determining whether the data is the familial fault; if the detected data is the known familial fault, the diagnosis conclusion is that the fault is detected, and the detected data is listed in a familial fault library for data supplement after the later diagnosis is confirmed; if unknown familial faults exist, the data of the field fault case library and the data of the laboratory fault simulation library are compared, the fault type is further determined, the diagnosis conclusion is that the faults exist, and the data are listed in the familial fault library for data supplement after the later diagnosis is confirmed.
Aiming at the condition that the diagnosis confidence coefficient is reduced, comparing the detection data given by the leading detection technology with the data of the familial fault library to further determine whether the data is the familial fault, and if the data is the known familial fault, judging that the diagnosis conclusion is the fault; if unknown familial faults exist, the data of the field fault case library and the data of the laboratory fault simulation library are compared. If the occurrence probability of the fault type given again after comparison is not less than 60%, the diagnosis conclusion is that the fault occurs, and if the occurrence probability of the fault type given again after comparison is less than 60%, the diagnosis conclusion is normal.
The patent library adopts a similar search method, and gives the occurrence probability of the fault type again, specifically: the patent library carries out correlation calculation on detection data (namely data to be diagnosed) given by a leading detection technology and all data (namely classical case data) of corresponding fault types in a field fault case library and a laboratory fault simulation library, calculates a correlation coefficient of the data, and gives out detection data again according to the size of the correlation coefficient as the occurrence probability of the fault type.
It should be emphasized that the embodiments described herein are illustrative rather than restrictive, and thus the present invention is not limited to the embodiments described in the detailed description, but also includes other embodiments that can be derived from the technical solutions of the present invention by those skilled in the art.
Claims (5)
1. A method for performing multivariate complementary cross validation on partial discharge diagnostic results is characterized by comprising the following steps:
step 1, carrying out partial discharge fault detection on the power equipment by using various partial discharge detection technologies;
step 2, if the detection result of one of the partial discharge detection technologies is judged to have a partial discharge fault, the partial discharge detection technology is used as a dominant detection technology to give a detection result; meanwhile, the rest other partial discharge detection technologies are used as an auxiliary detection technology set to perform multiple auxiliary detections on the power equipment from multiple aspects;
step 3, selecting whether to retest the power equipment or not according to the conditions of the multiple auxiliary detections, and simultaneously adjusting the diagnosis confidence coefficient of the leading detection technology; the specific implementation method of the step comprises the following steps:
step 3.1, if the auxiliary detection technology is concentrated with two or more detection technologies, judging that the power equipment has faults, improving the diagnosis confidence of the main detection technology, and executing step 4; if the auxiliary detection technology set only has the detection result of one detection technology to judge that the power equipment has faults, executing a step 3.2; if the auxiliary detection technology set does not have a detection result of one detection technology to judge that the power equipment has a fault, executing a step 3.3;
3.2, retesting the power equipment by the auxiliary detection technology set, if the auxiliary detection technology set has two or more detection results of the detection technologies in retesting to judge that the power equipment has faults, improving the diagnosis confidence of the leading detection technology, and executing the step 4; if the detection results of two or more detection technologies do not exist yet, the power equipment is judged to have faults, the diagnosis confidence coefficient of the leading detection technology is reduced, meanwhile, if the occurrence probability corresponding to the fault type given by the leading detection technology is not less than 60%, the step 4 is executed, and if the occurrence probability corresponding to the fault type given by the leading detection technology is less than 60%, the diagnosis conclusion is normal;
3.3, retesting the power equipment by an auxiliary detection technology set; if the auxiliary detection technology set has two or more detection results of the detection technologies in the retest to judge that the power equipment has faults, the diagnosis confidence coefficient of the leading detection technology is improved, and the step 4 is executed; if the detection results of two or more detection technologies do not determine that the power equipment has a fault, reducing the diagnosis confidence of the leading detection technology, and meanwhile, if the occurrence probability corresponding to the fault type given by the leading detection technology exceeds 80%, executing the step 4, and if the occurrence probability corresponding to the fault type given by the leading detection technology is lower than 80%, determining that the diagnosis conclusion is normal;
and 4, comparing the diagnosis data of the leading detection technology with the expert database set, and further determining the diagnosis.
2. The method of claim 1, wherein the partial discharge diagnosis result is cross-validated by multivariate complementation, the method comprising the steps of: the various partial discharge detection techniques in step 1 include a partial discharge detection technique for detecting temperature by infrared, a partial discharge detection technique for detecting chemical components by micro-water or oil chromatography, a partial discharge detection technique for detecting electromagnetic wave intensity by UHF and high frequency, and a partial discharge detection technique for detecting ultrasonic wave intensity by AE.
3. The method of claim 1, wherein the partial discharge diagnosis result is cross-validated by multivariate complementation, the method comprising the steps of: the detection result of the dominant detection technology in the step 2 comprises detection data, a fault type with the highest diagnosis possibility and the occurrence probability thereof.
4. The method of claim 1, wherein the partial discharge diagnosis result is cross-validated by multivariate complementation, the method comprising the steps of: the specific implementation method of the step 4 comprises the following steps:
aiming at the condition that the diagnosis confidence coefficient is improved, comparing the detection data given by the leading detection technology with the data of the familial fault library, and further determining whether the data is the familial fault; if the detected data is the known familial fault, the diagnosis conclusion is that the fault is detected, and the detected data is listed in a familial fault library for data supplement after the later diagnosis is confirmed; if unknown familial faults exist, comparing the data of the field fault case library with the data of the laboratory fault simulation library to further determine the fault type, and after the diagnosis is confirmed in the later period, listing the fault type in the familial fault library for data supplement;
aiming at the condition that the diagnosis confidence coefficient is reduced, comparing the detection data given by the leading detection technology with the data of the familial fault library to further determine whether the data is the familial fault, and if the data is the known familial fault, judging that the diagnosis conclusion is the fault; if the unknown familial fault is detected, comparing the data of the field fault case library with the data of the laboratory fault simulation library, if the probability of occurrence of the fault type given again after comparison is not less than 60%, determining that the fault is detected, if the probability of occurrence of the fault type given again after comparison is less than 60%, otherwise, determining that the fault is normal.
5. The method of claim 1 or 4, wherein the partial discharge diagnosis result is cross-validated by multivariate complementation, and the method comprises the following steps: the expert library set in the step 4 comprises a familial fault library, a field fault case library and a laboratory fault simulation library.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910433085.5A CN110208658B (en) | 2019-05-23 | 2019-05-23 | Method for performing multivariate complementary cross validation on partial discharge diagnosis result |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910433085.5A CN110208658B (en) | 2019-05-23 | 2019-05-23 | Method for performing multivariate complementary cross validation on partial discharge diagnosis result |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110208658A CN110208658A (en) | 2019-09-06 |
CN110208658B true CN110208658B (en) | 2021-03-19 |
Family
ID=67788341
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910433085.5A Active CN110208658B (en) | 2019-05-23 | 2019-05-23 | Method for performing multivariate complementary cross validation on partial discharge diagnosis result |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110208658B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111897855B (en) * | 2020-07-30 | 2023-11-10 | 广东省中山市质量计量监督检测所 | Electromagnetic compatibility performance diagnosis method and system |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011252780A (en) * | 2010-06-02 | 2011-12-15 | Tohoku Electric Power Co Inc | Detection method of partial discharge of electrical device using magnetic field probe |
CN104267315A (en) * | 2014-10-16 | 2015-01-07 | 山东大学 | Combined type island detection method based on initiative frequency shift and voltage amplitude change |
CN106358234A (en) * | 2016-09-23 | 2017-01-25 | 宁波大学 | A method for detecting master user signal normalized energy of synergetic cognitive radio network |
CN107316323A (en) * | 2017-06-28 | 2017-11-03 | 北京工业大学 | The non-reference picture method for evaluating quality set up based on multiscale analysis method |
CN107367676A (en) * | 2017-09-04 | 2017-11-21 | 厦门斯玛特思智能电气股份有限公司 | Partial discharge indicator based on audio intelligent identification |
CN108614170A (en) * | 2018-04-28 | 2018-10-02 | 国网山东省电力公司淄博供电公司 | A kind of power transformer synthesis monitor system |
CN108896878A (en) * | 2018-05-10 | 2018-11-27 | 国家电网公司 | A kind of detection method for local discharge based on ultrasound |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104655948A (en) * | 2013-11-21 | 2015-05-27 | 国家电网公司 | Novel multistage fault diagnosis method for power transformer |
US20170030957A1 (en) * | 2015-07-31 | 2017-02-02 | Aktiebolaget Skf | Partial discharge detection relay matrix for multiple lead analysis |
CN106597231B (en) * | 2016-11-11 | 2018-12-28 | 上海交通大学 | GIS fault detection system and method based on Multi-source Information Fusion and deep learning network |
CN109239516A (en) * | 2018-09-05 | 2019-01-18 | 国网山西省电力公司检修分公司 | Merge the transformer fault layering diagnostic method of a variety of intelligent diagnostics models |
CN109472097B (en) * | 2018-11-19 | 2022-09-20 | 国网湖北省电力有限公司黄石供电公司 | Fault diagnosis method for online monitoring equipment of power transmission line |
CN109670536B (en) * | 2018-11-30 | 2023-05-30 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Partial discharge signal clustering method under multi-source discharge and interference superposition condition |
-
2019
- 2019-05-23 CN CN201910433085.5A patent/CN110208658B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011252780A (en) * | 2010-06-02 | 2011-12-15 | Tohoku Electric Power Co Inc | Detection method of partial discharge of electrical device using magnetic field probe |
CN104267315A (en) * | 2014-10-16 | 2015-01-07 | 山东大学 | Combined type island detection method based on initiative frequency shift and voltage amplitude change |
CN106358234A (en) * | 2016-09-23 | 2017-01-25 | 宁波大学 | A method for detecting master user signal normalized energy of synergetic cognitive radio network |
CN107316323A (en) * | 2017-06-28 | 2017-11-03 | 北京工业大学 | The non-reference picture method for evaluating quality set up based on multiscale analysis method |
CN107367676A (en) * | 2017-09-04 | 2017-11-21 | 厦门斯玛特思智能电气股份有限公司 | Partial discharge indicator based on audio intelligent identification |
CN108614170A (en) * | 2018-04-28 | 2018-10-02 | 国网山东省电力公司淄博供电公司 | A kind of power transformer synthesis monitor system |
CN108896878A (en) * | 2018-05-10 | 2018-11-27 | 国家电网公司 | A kind of detection method for local discharge based on ultrasound |
Non-Patent Citations (5)
Title |
---|
《Application of extension neural network algorithm and chaos synchronization detection method to partial discharge diagnosis of power capacitor》;Meng-HuiWang等;《Measurement》;20181231;全文 * |
《基于多种检测技术的高压开关柜内部局部放电检测与分析》;李永祥等;《高压电器》;20170131;全文 * |
《基于局部放电监测的变压器故障诊断系统研究》;邵安海等;《四川电力技术》;20071231;全文 * |
《声—电—化联合检测在判别GIS自由金属颗粒放电缺陷上的应用》;李松原等;《高压电器》;20160930;全文 * |
《综述电力设备局部放电检测方法》;林松等;《电工文摘》;20160630;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN110208658A (en) | 2019-09-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103824137B (en) | A kind of complex mechanical equipment multi-state failure prediction method | |
CN115982602B (en) | Photovoltaic transformer electrical fault detection method | |
CN107480386B (en) | Test excitation optimization method based on response aliasing measurement and genetic algorithm | |
CN109187614B (en) | Metabonomics data fusion method based on nuclear magnetic resonance and mass spectrum and application thereof | |
CN106093771B (en) | A kind of circuit-breaker switching on-off coil current signal recognition methods | |
CN112149569B (en) | Voiceprint fault diagnosis method of transformer based on fuzzy C-means clustering algorithm | |
CN104007343A (en) | Transformer dynamic comprehensive fault diagnosis method based on Bayesian network | |
JP6789872B2 (en) | Analytical methods, analyzers, and programs | |
CN110703078A (en) | GIS fault diagnosis method based on spectral energy analysis and self-organizing competition algorithm | |
CN115800272A (en) | Power grid fault analysis method, system, terminal and medium based on topology identification | |
CN103399237A (en) | Method for detecting failure of oil-immersed transformer | |
CN110208658B (en) | Method for performing multivariate complementary cross validation on partial discharge diagnosis result | |
CN113391244A (en) | VMD-based transformer switching-on vibration signal characteristic frequency calculation method | |
CN105137354A (en) | Motor fault detection method based on nerve network | |
CN114397569A (en) | Circuit breaker fault arc detection method based on VMD parameter optimization and sample entropy | |
CN109960881B (en) | Process variable evaluation method based on Grangel causality | |
CN117269751B (en) | GIS isolating switch switching position confirmation method | |
CN116453437B (en) | Display screen module testing method, device, equipment and storage medium | |
CN113266921A (en) | Air conditioning equipment fault detection method, device, equipment and medium | |
CN114118166A (en) | Transformer fault diagnosis system and method based on intelligent frequency spectrum monitoring | |
CN116298719A (en) | Equipment insulation aging identification method and device, electronic equipment and storage medium | |
CN106443238B (en) | High-voltage equipment state evaluation method, online monitoring device evaluation method and device | |
CN115270410A (en) | GIS particle weak discharge development trend prediction method and system based on ARMA model | |
CN110703080B (en) | GIS spike discharge diagnosis method, discharge degree identification method and device | |
Sung-min et al. | The estimation of insulation on MV cables using the VLF tanδ diagnostic measurement |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |